From 87d4486698eaa0d4cd2f4f538a4d600eab47dfe2 Mon Sep 17 00:00:00 2001 From: Lukas Anzinger Date: Sun, 17 Jul 2016 14:20:20 +0200 Subject: Update derStandard.at and ORF.at (#183) * derStandard.at: Remove native ad links at the end of an article. * ORF.at: Fix extraction heuristic for author name. --- .orf.at.txt | 4 ++-- derstandard.at.txt | 1 + orf.at.txt | 4 ++-- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/.orf.at.txt b/.orf.at.txt index dd0f20b..9eb29c3 100644 --- a/.orf.at.txt +++ b/.orf.at.txt @@ -3,8 +3,8 @@ single_page_link: //div[@id='ss-storyText']//p[contains(., 'Mehr dazu')]/a title: substring-before(//title,' - ') body: //div[@id="ss-storyText"] -author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF')], ', ORF') -strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF')] +author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')], ', ORF.at') +strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')] date: substring-after(//div[@class='storyMeta socialshare']//p[@class='date'],'Publiziert am') strip: //p[@class='date'] diff --git a/derstandard.at.txt b/derstandard.at.txt index 8c84a5c..61ad6fc 100644 --- a/derstandard.at.txt +++ b/derstandard.at.txt @@ -15,6 +15,7 @@ strip: //div[@class='credits'] strip: //div[@id='feature-cover'] strip: //div[@id='feature-meta'] strip: //li[@class='empty'] +strip: //ul[@class='lookup-links'] prune: no tidy: no diff --git a/orf.at.txt b/orf.at.txt index dd0f20b..9eb29c3 100644 --- a/orf.at.txt +++ b/orf.at.txt @@ -3,8 +3,8 @@ single_page_link: //div[@id='ss-storyText']//p[contains(., 'Mehr dazu')]/a title: substring-before(//title,' - ') body: //div[@id="ss-storyText"] -author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF')], ', ORF') -strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF')] +author: substring-before(//div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')], ', ORF.at') +strip: //div[@id="ss-storyText"]//p[contains(text(), ', ORF.at')] date: substring-after(//div[@class='storyMeta socialshare']//p[@class='date'],'Publiziert am') strip: //p[@class='date'] -- cgit v1.3.1